Merge pull request #4 from nadar/encode-url

add encoding option and test

CHANGELOG.md

@@ -3,6 +3,10 @@
 All notable changes to this project will be documented in this file. This project adheres to [Semantic Versioning](http://semver.org/).
 In order to read more about upgrading and BC breaks have a look at the [UPGRADE Document](UPGRADE.md).
 
+## 1.1.0 (21. October 2020)
+
++ [#4](https://github.com/nadar/crawler/pull/4) Add option to encode the url paths.
+
 ## 1.0.0 (25. September 2020)
 
 - First stable release.

src/Url.php

@@ -22,6 +22,12 @@ class Url
      */
     protected $parsed;
 
+    /**
+     * @var boolean Whether values should be encoded when retrieving values or not. By default this is disabled.
+     * @since 1.1.0
+     */
+    public $encode = false;
+
     /**
      * Constructor
      *
@@ -79,7 +85,7 @@ public function getHost()
      */
     public function getPath()
     {
-        return isset($this->parsed['path']) ? $this->parsed['path'] : false;
+        return isset($this->parsed['path']) ? $this->processEncoding($this->parsed['path']) : false;
     }
 
     /**
@@ -99,7 +105,7 @@ public function getPathExtension()
      */
     public function getPathFileName()
     {
-        return basename($this->getPath());
+        return $this->processEncoding(basename($this->getPath()));
     }
 
     /**
@@ -167,4 +173,16 @@ public function merge(Url $url)
 
         return $this;
     }
+
+    /**
+     * Process a value which will be encoded when enabled. If not the value will be the same from input.
+     *
+     * @param string $value
+     * @return string If encoding is enabled the value will be encoded otherwise return original.
+     * @since 1.1
+     */
+    private function processEncoding($value)
+    {
+        return $this->encode ? urlencode($value) : $value;
+    }
 }

tests/UrlTest.php

@@ -41,4 +41,22 @@ public function testMerge()
         $this->assertSame('nadar.io', $b->merge($a)->getHost()); // nothing will happen as host exists
         $this->assertSame('https', $b->merge($a)->getScheme()); // nothing will happen as scheme exists
     }
+
+    public function testEncode()
+    {
+        // https://www.ahv-iv.ch/de/Merkblätter-Formulare/Formulare/Elektronische-Formulare/AHV-Formulare/318260-Anmeldung-für-einen-Versicherungsausweis
+        // https://www.ahv-iv.ch/it/Opuscoli-Moduli/Moduli/Prestazioni-dellIPG-servizio-e-maternità
+
+        $u = new Url('https://www.ahv-iv.ch/de/Merkblätter-Formulare/Formulare/Elektronische-Formulare/AHV-Formulare/318260-Anmeldung-für-einen-Versicherungsausweis');
+        $u->encode = true;
+
+        $this->assertSame('%2Fde%2FMerkbl%C3%A4tter-Formulare%2FFormulare%2FElektronische-Formulare%2FAHV-Formulare%2F318260-Anmeldung-f%C3%BCr-einen-Versicherungsausweis', $u->getPath());
+
+        $u = new Url('https://luya.io/äà');
+        $this->assertSame('https://luya.io/äà', $u->getNormalized());
+
+        $u = new Url('https://luya.io/äà');
+        $u->encode = true;
+        $this->assertSame('https://luya.io/%2F%C3%A4%C3%A0', $u->getNormalized());
+    }
 }